ISM Assignment #1, Part 2

Load packages and data

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.4     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   2.0.1     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:purrr':
## 
##     discard

## The following object is masked from 'package:readr':
## 
##     col_factor

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(lemon)

## 
## Attaching package: 'lemon'

## The following object is masked from 'package:purrr':
## 
##     %||%

## The following objects are masked from 'package:ggplot2':
## 
##     CoordCartesian, element_render

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

moviesAreTheBest <- read.csv("movie_profit-1.csv")
options(scipen = 999)

#1

# Create a bar chart for worldwide gross by genre
ggplot(data=moviesAreTheBest) +
  aes(x=genre, y = worldwide_gross) + # set axis input data
  labs(title = "Worldwide Gross Revenue per Genre", 
       x = "Genre", y = "Worldwide Gross Revenue") + # set axis labels
  geom_bar(stat = "identity")

#2

# Create a bar chart for worldwide gross by genre for each  MPAA Rating
moviesAreTheBest %>%
  ggplot(aes(x = genre, y = worldwide_gross)) + 
  scale_y_continuous(labels = dollar_format()) + # set $ to y-axis values
  geom_bar(stat = "identity") +
  labs(title = "Genre and Worldwide Gross Revenue by MPAA Rating", 
       x = "Genre", y = "Worldwide Gross Revenue") + # set axis labels
  facet_rep_wrap(~mpaa_rating, repeat.tick.labels = TRUE) # repeat graph for each MPAA rating

#3

# Create a bar chart for worldwide gross by MPAA rating for each genre
# NOTE: Mistakes identified in comments below
ggplot(data = moviesAreTheBest) + 
  aes(x = mpaa_rating, y = worldwide_gross) + 
  scale_y_continuous(labels = dollar_format()) + # missing parens 
  geom_bar(stat = "identity") + # missing stat = identity 
  labs(title = "Worldwide Gross Revenue by MPAA Rating", x = "MPAA Rating", y = "Worldwide Gross Revenue") + 
  facet_rep_wrap(~genre, repeat.tick.labels = TRUE) #facet_rep_wrap not facet_wrap

Issue #1: Missing end parenthesis on the 3rd line

Issue #2: Missing stat = “identity” argument on 4th line to enable y-axis input data

Issue #3: facet_rep_wrap is the function needed to enable repeat.tick.labels argument

#4

# Create a scatter plot for domestic gross by production budget for each MPAA Rating
moviesAreTheBest %>%
   ggplot(aes(x =production_budget, y = domestic_gross)) +
   geom_point() +
  labs(title = "MPAA Rating and Domestic Gross Revenue by Production Budget", 
       x = "Production Budget", y = "Domestic Gross Revenue") +
   facet_rep_wrap(~mpaa_rating, repeat.tick.labels = TRUE) # repeat graph for each MPAA rating

#5

# Create a line graph to count movies made per year
moviesAreTheBest %>%
  mutate(year = year(release_date)) %>% # get the year from the release date
  group_by(year) %>% # group each movie into year released
  ggplot(aes(x=year)) +
  labs(title = "Total Movies Released by Year", 
       x = "Year", y = "Total Movies Released") +
  geom_line(stat="bin")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

#6

# Create a histogram for distribution of Universal films by production budget for each genre
moviesAreTheBest %>%
  filter(distributor == "Universal") %>% # filter for Universal movies only
  ggplot(aes(x = production_budget, fill = mpaa_rating)) + #color MPAA rating in each bar
  scale_x_continuous(labels = dollar_format()) +
  geom_histogram() +
  labs(title = "Distribution of Movies by Production Budget", 
     x = "Production Budget", y = "Total Movies", fill = "MPAA Rating") +
  facet_rep_wrap(~genre, repeat.tick.labels = TRUE) 

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

For each genre you can see the range of production budgets for various movies on the x-axis, which is then broken down by the MPAA rating. So by looking at the chart, it is evident that rated R and PG-13 movies have the highest production budgets compared to the other ratings. The only exception is for the adventure genre, where many PG rated movies also have the high production budget.

#7 part 1

# Create a boxplot for worldwide gross by MPAA rating 
movie_boxplot <- moviesAreTheBest %>%
  ggplot(aes(x=mpaa_rating,y=worldwide_gross, fill=mpaa_rating)) + #color mpaa rating with fill
  geom_boxplot(show.legend = FALSE)+
  labs(title = "Worldwide Gross Revenue by MPAA Rating", 
       x = "MPAA Rating", y = "Worldwide Gross Revenue") +
  coord_flip() # rotate boxplot to view horizontally, instead of vertically

ggplotly(movie_boxplot) # make the graph interactive

#7 part 2

# Create a boxplot for worldwide gross by MPAA rating for Universal films
movie_boxplot <- moviesAreTheBest %>%
  filter(distributor == "Universal") %>% # filter for Universal movies only
  ggplot(aes(x=mpaa_rating,y=worldwide_gross, fill = mpaa_rating)) + #color mpaa rating with fill
  geom_boxplot(show.legend = FALSE) +
  labs(title = "Worldwide Gross Revenue by MPAA Rating for Universal Films", 
       x = "MPAA Rating", y = "Worldwide Gross Revenue") +
  coord_flip() # rotate boxplot to view horizontally 

ggplotly(movie_boxplot) # make the graph interactive

For each boxplot represented, rated PG-13 and rated G movies appeared right-skewed, while PG and rated R movies appeared symmetrical. In addition, all rated movies except rated G movies had upper-limit outliers.

#8 part 1

# Create a polar chart to view distribution of movies by genre
moviesAreTheBest %>%
  ggplot(aes(x = genre, y = "", fill = genre)) + 
  geom_bar(stat = "identity") +
  labs(title = "Distribution of Movies by Genre", 
       x = "Total Movies", y = "Total Movies") +
  coord_polar("x", start = 0)

In this polar chart, we can see that there are more movies produced in the Drama genre than any other genre. Conversely, Horror is the genre with the least amount of movies being produced.

#8 part 2

# Create a stacked bar chart to compare distribution of movies by MPAA Rating from 3 studios
stackedBarChart <- moviesAreTheBest %>%
  filter(distributor %in% c("Universal", "Warner Bros", "Sony Pictures")) %>% # filter these 3 studios
  ggplot(aes(x=distributor, fill=mpaa_rating)) + # color MPAA ratings to make stacked bars
  labs(title = "Distribution of Movies by MPAA Rating for 3 Studios", 
       x = "Distributor", y = "Total Movies", fill="MPAA Rating") +
  geom_bar()
  
ggplotly(stackedBarChart)

Looking at the rating distribution for 3 studios’ films, we can see that these studios produce significantly more PG-13 and R-rated movies than any other rating. For example, Universal has released almost an equal number of PG-13 (119) and R-rated (111) movies, however they have released relatively very few G-rated movies (7). Of these 3 studios, Warner Bros has released the greatest number of R-rated movies (157), and Sony Pictures has released the greatest number of PG-13 movies (138).